Generating Synthetic EEG Data for Psychiatric Disorders with Variational Autoencoders

Date

2025-01-01

Author

Çınar, Burcu

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

250
views

0
downloads

Cite This

This study explores the application of Variational Autoencoders (VAEs) for generating synthetic electroencephalography (EEG) data pertinent to psychiatric disorders. Using the Kaggle EEG Psychiatric Disorders dataset [21], multiple VAE models were developed and trained to capture the intricate patterns associated with various mental health conditions. The findings indicate that the synthetic EEG data produced by some of these models may closely mirror some of the statistical properties of the original dataset, suggesting the potential of VAEs in augmenting EEG data. This approach not only addresses challenges related to data scarcity but also opens avenues for improved diagnostic tools and personalised treatment strategies in psychiatry. The project codes can be found in the GitHub Repository [5].

Subject Keywords

electroencephalography (EEG), generative modelling, psychiatric disorders, synthetic data generation, variational autoencoders (VAEs)

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105008417099&origin=inward
https://hdl.handle.net/11511/115370

Collections

Graduate School of Informatics, Conference / Seminar